Predicting unseen antibodies’ neutralizability via adaptive graph neural networks

Zhang, Jie; Du, Yishan; Zhou, Jin; Ding, Jinru; Xia, Shuai; Wang, Qian; Chen, Feiyang; Zhou, Mu; Zhang, Xuemei; Wang, Weifeng; Wu, Hongyan; Lu, Lu; Zhang, Shaoting

doi:10.1038/s42256-022-00553-w

Cited by 15 publications

(12 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Naturally, high-quality data insufficiency presents an obstacle to training deep-learning models with ideal generalization capability. In contrast, sequence-only methods, which take advantage of extensive antibody sequence data, offer a more efficient framework for large-scale antibody screening [28][29][30][31][32][33]. Earlier studies, such as ProABC [28], utilized a sequenceonly random forest algorithm to predict paratope residues, eliminating the need for structured data to achieve accurate predictions.…”

Section: Introductionmentioning

confidence: 99%

Interpretable antibody-antigen interaction prediction by introducing route and priors guidance

Liu,

Nie,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

With the application of personalized and precision medicine, more precise and efficient antibody drug development technology is urgently needed. Identification of antibody-antigen interactions is key to antibody engineering. The time-consuming and expensive nature of wet-lab experiments calls for efficient computational methods. Previous deep-learning-based computing methods for antibody-antigen interaction prediction are distinctly divided into two categories: structure-based and sequence-based. Taking into account the non-overlapping advantage of these two major categories, we propose an interpretable antibody-antigen interaction prediction method, S3AI, that bridges structures to sequences through structural information distillation. Furthermore, non-covalent interactions are modeled explicitly to guide neural networks in understanding the underlying patterns in antigen-antibody docking. Supported by the two innovative designs mentioned above, S3AI significantly and comprehensively surpasses the state-of-the-art models. S3AI maintains excellent robustness when predicting unknown antibody-antigen pairs, surpassing specialized prediction methods designed for out-of-distribution generalization in fair comparisons. More importantly, S3AI captures the universal pattern of antibody-antigen interactions, which not only identifies the CDRs responsible for specific binding to the antigen but also unearthed the importance of CDR-H3 for the interaction. The implicit introduction of knowledge of structure modality and the explicit modeling of chemical constraints build a 'sequence-to-function' route, thereby facilitating S3AI's understanding of complex molecular interactions through providing route and priors guidance. S3AI, which does not require structure input, is suitable for large-scale, parallelized antibody optimization and screening while outperforming state-of-the-art prediction methods. It helps to quickly and accurately identify potential candidates in the vast antibody space, thereby accelerating the development process of antibody drugs.

show abstract

Section: Introductionmentioning

confidence: 99%

Interpretable antibody-antigen interaction prediction by introducing route and priors guidance

Liu,

Nie,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In the past few years, the use of machine learning techniques has revolutionized the field of computational materials science by allowing researchers to simulate complex multicomponent systems at a significantly reduced computational footprint than brute-force quantum simulation methods, such as density functional theory (DFT) calculations or higher fidelity electronic structure methods like quantum Monte Carlo (QMC), and coupled cluster singles and doubles (CCSD). − Notable application areas include drug discovery, screening of materials from a huge database for target functional applications and design of materials with tailored properties. − To this end, hundreds of neural network (NN) and graph neural network (GNN) models have been proposed in the past few years. While a few earlier models, such as those in refs − , used empirical, physics-inspired features, recent models − learn the local environment around an atom directly from the data during model training.…”

Section: Introductionmentioning

confidence: 99%

Graph-EAM: An Interpretable and Efficient Graph Neural Network Potential Framework

Yang

Chen

Sun

et al. 2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

The development of deep learning interatomic potentials has enabled efficient and accurate computations in quantum chemistry and materials science, circumventing computationally expensive ab initio calculations. However, the huge number of learnable parameters in deep learning models and their complex architectures hinder physical interpretability and affect the robustness of the derived potential. In this work, we propose graph-EAM, a lightweight graph neural network (GNN) inspired by the empirical embedded atom method to model the interatomic potential of single-element structures. Four material systems: platinum, niobium, silicon, and amorphous-carbon, for which quantum simulation data sets are publicly available, are examined to demonstrate that graph-EAM can achieve high energy and force prediction accuracy�comparable or better than existing state-of-the-art machine learning models�with much fewer parameters. It is also shown that the explicit inclusion of the angular information via three-body atomic density increases the prediction accuracy. The accuracy and efficiency of potentials obtained from graph-EAM can help accelerate the molecular dynamics simulation.

show abstract

“…However, collecting confident protein structures through wet-lab experiments is a time-consuming and labor-intensive process 25 . Some other methods utilize antibody sequences, which are relatively cheaper and easier to obtain, to predict affinity for specific antibodies 26,27 . Although such methods employ large-scale pre-trained language models to achieve even more accurate affinity predictions 28,29 , their prediction ability is limited to the trained antigens since they do not consider the antigen information.…”

Section: Introductionmentioning

confidence: 99%

De novogeneration of antibody CDRH3 with a pre-trained generative large language model

He,

Guan

et al. 2023

Preprint

View full text Add to dashboard Cite

Artificial Intelligence (AI) techniques have made great advances in assisting antibody design. However, antibody design still heavily relies on isolating antigen-specific antibodies from serum, which is a resource-intensive and time-consuming process. To address this issue, we propose a Pre-trained Antibody generative large Language Model (PALM) for the de novo generation of artificial antibodies heavy chain complementarity-determining region 3 (CDRH3) with desired antigen-binding specificity, reducing the reliance on natural antibodies. We also build a high-precision model antigen-antibody binder (A2binder) that pairs antigen epitope sequences with antibody sequences to predict binding specificity and affinity. PALM-generated antibodies exhibit binding ability to SARS-CoV-2 antigens, including the emerging XBB variant, as confirmed through in-silico analysis and in-vitro assays. The in-vitro assays validated that PALM-generated antibodies achieve high binding affinity and potent neutralization capability against both wild-type and XBB spike proteins of SARS-CoV-2. Meanwhile, A2binder demonstrated exceptional predictive performance on binding specificity for various epitopes and variants. Furthermore, by incorporating the attention mechanism into the PALM model, we have improved its interpretability, providing crucial insights into the fundamental principles of antibody design.

show abstract

Predicting unseen antibodies’ neutralizability via adaptive graph neural networks

Cited by 15 publications

References 53 publications

Interpretable antibody-antigen interaction prediction by introducing route and priors guidance

Interpretable antibody-antigen interaction prediction by introducing route and priors guidance

Graph-EAM: An Interpretable and Efficient Graph Neural Network Potential Framework

De novogeneration of antibody CDRH3 with a pre-trained generative large language model

Contact Info

Product

Resources

About